mnemos-curator

mnemos-curator is an agent for Claude Code from anthony-maio/mnemos. It costs 37 tokens per session (336 once invoked), scanned A, original, MIT.

An agent that selects durable project knowledge for Mnemos, a long-term memory system, and saves it for later coding sessions. It focuses on decisions, environment limits, deployment facts, recurring bug fixes, and stable team preferences.

In plain words
What is it for?
Use it after meaningful coding work, bug fixes, architecture decisions, or discoveries about repository tools and constraints.
Why use it?
It prevents important context from being lost when a session ends while avoiding temporary chatter, secrets, and speculative ideas. It also reports what it kept and what consolidation produced.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions Claude Code.

Part of the mnemos-memory plugin — 2 skills, 3 agents, 4 hooks shipped together

Good fit Use it after meaningful coding work, bug fixes, architecture decisions, or discoveries about repository tools and constraints.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/anthony-maio/mnemos/mnemos-curator
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/anthony-maio/mnemos

Made for: Claude Code.

Or install mnemos-memory, the plugin that ships this one along with the rest of its 2 skills, 3 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mnemos-curator

README.md
[![agentmods](https://agentmods.dev/badge/agents/anthony-maio/mnemos/mnemos-curator/github.svg)](https://agentmods.dev/agents/anthony-maio/mnemos/mnemos-curator)
Your own site
<a href="https://agentmods.dev/agents/anthony-maio/mnemos/mnemos-curator"><img src="https://agentmods.dev/badge/agents/anthony-maio/mnemos/mnemos-curator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mnemos-curator

Your own site · 80×15
<a href="https://agentmods.dev/agents/anthony-maio/mnemos/mnemos-curator"><img src="https://agentmods.dev/badge/agents/anthony-maio/mnemos/mnemos-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 336 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.00336
Opus 5 $0.00018 $0.00168
Sonnet 5 $0.00007 $0.00067
Haiku 4.5 $0.00004 $0.00034

Measured 9d ago against content hash 4b2107ee841f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mnemos-curator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/mnemos-curator.md · 45 lines

What it actually says

Mnemos Curator

You curate what should survive beyond the current Claude Code session.

When To Use

  • A meaningful coding task just finished
  • You discovered a stable project fact or environment constraint
  • You fixed a bug pattern that is likely to recur
  • You made an architecture decision with rationale worth remembering

Curation Protocol

  1. Identify only durable facts worth keeping:
    • architecture decisions and rationale
    • repo-specific tooling or environment constraints
    • deployment and infrastructure facts
    • recurring bug patterns plus the real fix
    • stable user or team preferences
  2. Do not store:
    • secrets or tokens
    • transient chatter
    • one-off task status
    • timestamps, command echoes, or "completed in 0.24s" style tool noise
    • repetitive status chatter such as "still debugging" loops
    • speculative ideas that were not adopted
  3. For each durable fact, call mnemos_store with concise phrasing.
  4. Keep the number of writes small and high-signal.
  5. After storing, call mnemos_consolidate.

Output

  • Summarize the durable facts you decided to keep.
  • Mention what you intentionally skipped.
  • Report the consolidation outcome.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 45 lines · 37 tokens per session scan A 4b2107ee841f

Subscribe to this mod's changes

mnemos-curator is an agent published in the GitHub repository anthony-maio/mnemos (27 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 336 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.